+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: is RDNA worth the hassle yet for FLUX (/showthread.php?tid=437)
Pages:
1
2
is RDNA worth the hassle yet for FLUX - quantghost - 09-24-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: Ollama on M3 Max, keeping reranking in mind from the start.
Feel free to tear it apart if you see something dumb.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
I expected the biggest difference to come from the model, but the stack around it mattered at least as much.
Re: is RDNA worth the hassle yet for FLUX - cozykite - 09-24-2026
I think the bottleneck is somewhere else. I get why that seems right, but on 4090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: is RDNA worth the hassle yet for FLUX - batchyard - 09-24-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: is RDNA worth the hassle yet for FLUX - mangofield33 - 09-24-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: is RDNA worth the hassle yet for FLUX - rocmriley - 09-24-2026
Quote:Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Good point. The pattern around prefill/decode split has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: is RDNA worth the hassle yet for FLUX - phasetrack - 09-25-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: is RDNA worth the hassle yet for FLUX - northhall88 - 09-28-2026
Need a little more detail here. Are you testing this on 5090 or something else?
Re: is RDNA worth the hassle yet for FLUX - mangofield33 - 09-29-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: is RDNA worth the hassle yet for FLUX - tensorworks - 10-02-2026
Quote:Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quali
Good point. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: is RDNA worth the hassle yet for FLUX - torchsmith25 - 10-02-2026
that fixed it for me too.